agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v10 6/6] Expose WAL usage counters in verbose (auto)vacuum output. 9640+ messages / 2 participants [nested] [flat]
* [PATCH v10 6/6] Expose WAL usage counters in verbose (auto)vacuum output. @ 2020-03-19 15:08 Julien Rouhaud <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Julien Rouhaud @ 2020-03-19 15:08 UTC (permalink / raw) Author: Julien Rouhaud Reviewed-by: Fuji Masao Discussion: https://postgr.es/m/CAB-hujrP8ZfUkvL5OYETipQwA=e3n7oqHFU=4ZLxWS_Cza3kQQ@mail.gmail.com --- src/backend/access/heap/vacuumlazy.c | 24 +++++++++++++++++++++++- src/backend/commands/explain.c | 2 +- 2 files changed, 24 insertions(+), 2 deletions(-) diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c index cc7e8521a5..735087dd74 100644 --- a/src/backend/access/heap/vacuumlazy.c +++ b/src/backend/access/heap/vacuumlazy.c @@ -410,6 +410,8 @@ heap_vacuum_rel(Relation onerel, VacuumParams *params, int nindexes; PGRUsage ru0; TimestampTz starttime = 0; + WalUsage walusage_start = pgWalUsage; + WalUsage walusage = {0, 0, 0}; long secs; int usecs; double read_rate, @@ -614,6 +616,9 @@ heap_vacuum_rel(Relation onerel, VacuumParams *params, TimestampDifference(starttime, endtime, &secs, &usecs); + memset(&walusage, 0, sizeof(WalUsage)); + WalUsageAccumDiff(&walusage, &pgWalUsage, &walusage_start); + read_rate = 0; write_rate = 0; if ((secs > 0) || (usecs > 0)) @@ -666,7 +671,13 @@ heap_vacuum_rel(Relation onerel, VacuumParams *params, (long long) VacuumPageDirty); appendStringInfo(&buf, _("avg read rate: %.3f MB/s, avg write rate: %.3f MB/s\n"), read_rate, write_rate); - appendStringInfo(&buf, _("system usage: %s"), pg_rusage_show(&ru0)); + appendStringInfo(&buf, _("system usage: %s\n"), pg_rusage_show(&ru0)); + appendStringInfo(&buf, + _("WAL usage: %ld records, %ld full page writes, " + UINT64_FORMAT " bytes"), + walusage.wal_records, + walusage.wal_num_fpw, + walusage.wal_bytes); ereport(LOG, (errmsg_internal("%s", buf.data))); @@ -758,6 +769,8 @@ lazy_scan_heap(Relation onerel, VacuumParams *params, LVRelStats *vacrelstats, IndexBulkDeleteResult **indstats; int i; PGRUsage ru0; + WalUsage walusage_start = pgWalUsage; + WalUsage walusage = {0, 0, 0}; Buffer vmbuffer = InvalidBuffer; BlockNumber next_unskippable_block; bool skipping_blocks; @@ -1727,6 +1740,15 @@ lazy_scan_heap(Relation onerel, VacuumParams *params, LVRelStats *vacrelstats, "%u pages are entirely empty.\n", empty_pages), empty_pages); + + memset(&walusage, 0, sizeof(WalUsage)); + WalUsageAccumDiff(&walusage, &pgWalUsage, &walusage_start); + appendStringInfo(&buf, _("%ld WAL records, %ld WAL full page writes, " + UINT64_FORMAT " WAL bytes\n"), + walusage.wal_records, + walusage.wal_num_fpw, + walusage.wal_bytes); + appendStringInfo(&buf, _("%s."), pg_rusage_show(&ru0)); ereport(elevel, diff --git a/src/backend/commands/explain.c b/src/backend/commands/explain.c index b05b55979b..f7f1c3efce 100644 --- a/src/backend/commands/explain.c +++ b/src/backend/commands/explain.c @@ -3105,7 +3105,7 @@ show_wal_usage(ExplainState *es, const WalUsage *usage) { ExplainPropertyInteger("WAL records", NULL, usage->wal_records, es); - ExplainPropertyInteger("WAL full page records", NULL, + ExplainPropertyInteger("WAL full page writes", NULL, usage->wal_num_fpw, es); ExplainPropertyUInteger("WAL bytes", NULL, usage->wal_bytes, es); -- 2.20.1 --BXVAT5kNtrzKuDFl-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --k4rn5ob3nx2ufkij-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
* [PATCH 5/5] Use BulkInsertState when copying data to the new heap. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 9640+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) It should make the copying more efficient. Besides that, buffer access strategy is involved this way. This diff reverts the changes done in previous parts of the series to reform_and_rewrite_tuple() and introduces a separate function heap_insert_for_repack(). --- src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++-------- 1 file changed, 72 insertions(+), 38 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index f4c62e5bc7a..50ddee9d8c8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -49,6 +49,11 @@ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); +static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull, + BulkInsertState bistate); +static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, + Relation NewHeap, Datum *values, bool *isnull); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double *tups_recently_dead) { RewriteState rwstate = NULL; + BulkInsertState bistate = NULL; IndexScanDesc indexScan; TableScanDesc tableScan; HeapScanDesc heapScan; @@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (!concurrent) rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff, *multi_cutoff); + else + bistate = GetBulkInsertState(); /* Set up sorting if wanted */ @@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, }; int64 ct_val[2]; - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, + values, isnull, rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, break; n_tuples += 1; - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + if (!concurrent) + reform_and_rewrite_tuple(tuple, + OldHeap, NewHeap, + values, isnull, + rwstate); + else + heap_insert_for_repack(tuple, OldHeap, NewHeap, + values, isnull, bistate); + /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); @@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); + if (bistate) + FreeBulkInsertState(bistate); /* Clean up */ pfree(values); @@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * SET WITHOUT OIDS. * * So, we must reconstruct the tuple from component Datums. - * - * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that - * case we still need to deform/form the tuple. TODO Shouldn't we rename the - * function, as might not do any rewrite? */ static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate) +{ + HeapTuple copiedTuple; + + copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + /* The heap rewrite module does the rest */ + rewrite_heap_tuple(rwstate, tuple, copiedTuple); + + heap_freetuple(copiedTuple); +} + +/* + * Insert tuple when processing REPACK CONCURRENTLY. + * + * rewriteheap.c is not used in the CONCURRENTLY case because it'd be + * difficult to do the same in the catch-up phase (as the logical + * decoding does not provide us with sufficient visibility + * information). Thus we must use heap_insert() both during the + * catch-up and here. + * + * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical + * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops + * this relation, so no logical replication subscription should need the data. + * + * BulkInsertState is used because many tuples are inserted in the typical + * case. + */ +static void +heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull, BulkInsertState bistate) +{ + tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + + heap_insert(NewHeap, tuple, GetCurrentCommandId(true), + HEAP_INSERT_NO_LOGICAL, bistate); + + heap_freetuple(tuple); +} + +/* + * Deform tuple, set values of dropped columns to NULL, form a new tuple and + * return it. + */ +static HeapTuple +reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, + Datum *values, bool *isnull) { TupleDesc oldTupDesc = RelationGetDescr(OldHeap); TupleDesc newTupDesc = RelationGetDescr(NewHeap); - HeapTuple copiedTuple; int i; heap_deform_tuple(tuple, oldTupDesc, values, isnull); - /* Be sure to null out any dropped columns */ for (i = 0; i < newTupDesc->natts; i++) { if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) isnull[i] = true; } - copiedTuple = heap_form_tuple(newTupDesc, values, isnull); - - if (rwstate) - /* The heap rewrite module does the rest */ - rewrite_heap_tuple(rwstate, tuple, copiedTuple); - else - { - /* - * Insert tuple when processing REPACK CONCURRENTLY. - * - * rewriteheap.c is not used in the CONCURRENTLY case because it'd be - * difficult to do the same in the catch-up phase (as the logical - * decoding does not provide us with sufficient visibility - * information). Thus we must use heap_insert() both during the - * catch-up and here. - * - * The following is like simple_heap_insert() except that we pass the - * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps - * the relation files, it drops this relation, so no logical - * replication subscription should need the data. - */ - heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, NULL); - } - - heap_freetuple(copiedTuple); + return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 9640+ messages in thread
end of thread, other threads:[~2026-03-09 10:35 UTC | newest] Thread overview: 9640+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-03-19 15:08 [PATCH v10 6/6] Expose WAL usage counters in verbose (auto)vacuum output. Julien Rouhaud <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 4/4] Use BulkInsertState when copying data to the new heap. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 5/5] Use BulkInsertState when copying data to the new heap. 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